Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the readOnlyHint/openWorldHint/idempotentHint annotations by disclosing the exact refusal behavior, refusal_reason enum values, the evidence-as-verbatim-quote constraint, the internal routing over 5,798 tools and 1,517 sources, and the extra LLM call cost. This gives the agent a precise model of what will happen and what could go wrong, with no contradiction to the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but efficient: it front-loads the core identity and safety guarantee, then the return/refusal contract, then situational guidance, then the cost trade-off. Every sentence adds distinct value, and the structured flow from behavior to usage to exclusion makes it easy to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no output schema, the description compensates fully by specifying the success return shape, the refusal shape, refusal reason variants, and the safety-use context. Combined with the annotations covering mutability and world scope, an agent has enough information to decide when to invoke this tool and what to expect.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already fully documents the question parameter and its aliases. The description does not add parameter-level guidance beyond stating that it 'fills arguments' internally, but that is process context rather than parameter semantics. Baseline 3 is appropriate because the description need not duplicate schema info.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource (ask Pipeworx) plus a distinct mode: grounded, hallucination-resistant answering. It explicitly differentiates itself from ask_pipeworx by describing the extraction behavior, evidence output, and refusal mechanism, so an agent can distinguish sibling tools without inspecting schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit when-to-use guidance: whenever an answer will be quoted, cited, or acted on and facts must not be invented, with concrete examples like financial verdicts, legal claims, medical lookups, and public statements. It also says when NOT to use it (prefer ask_pipeworx for casual lookups) and explains the cost trade-off of one extra LLM call.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.